I have to run LRT to compare two logistic regression models. when I run the code below I noticed the output seems identical. In this scenario are these identical tests? If so in what scenario would they be different?

input_null <- mtcars[,c("am","cyl","hp")]
null_fit <- glm(formula = am ~ cyl + hp, data = input_null , family = binomial)

input_full <- mtcars[,c("am","cyl","hp", "wt")]
full_fit <- glm(formula = am ~ cyl + hp + wt, data = input_full , family = binomial)

chisq <- anova(null_fit, full_fit, test='Chisq')
lrt <- anova(null_fit, full_fit, test='LRT')

1 Answer 1


Please read the documentation for ?anova.glm.

You can also choose "LRT" and "Rao" for likelihood ratio tests and Rao's efficient score test. The former is synonymous with "Chisq" (although both have an asymptotic chi-square distribution).

"LRT" and "Chisq" are synonymous; they both trigger the same calculations.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.